All skills
simota avatar

/scribe

@35ffd55
by shingo imotasimota/agent-skills85 stars
15

Authoring standalone and cross-team specifications: PRD/SRS/HLD/LLD, staged L0-L4 unified packages, BDD acceptance criteria, and traceability. Use for technical or multi-audience documentation; not implementation or architecture decisions.

Use this Skill: https://skilld.dev/gh/simota/agent-skills/scribe

This session only. Nothing lands on disk.

referencereference-index.md

≈887 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Scribe Reference Index

Every reference/ file scribe owns, and the condition that makes it worth reading. scribe/SKILL.md keeps only the shared-contract rows and a pointer here.

Read this when you need a reference and the Recipe registry did not already name it, or when scanning what this skill can consult at all.


Reference Read This When
reference/prd-template.md A PRD, quick PRD, or PRD quality checks.
reference/srs-template.md Technical requirements, interfaces, measurable NFRs.
reference/design-template.md HLD, LLD, scaling strategy, config, rollback sections.
reference/checklist-template.md Implementation, review, or quick delivery checklists.
reference/test-spec-template.md Test plans, traceability, Gherkin structure.
reference/adr-writing.md adr — Nygard/MADR format, numbering, immutability, supersede chains.
reference/runbook-writing.md runbook — symptom/triage/recover/verify structure, idempotency, escalation, rollback.
reference/api-documentation.md api-doc — OpenAPI to human-facing reference docs with samples, error catalogs, auth flows.
reference/anti-patterns.md A draft is weak, vague, bloated, untestable, or shows AI-generation artifacts.
reference/documentation-calibration.md INSCRIBE tracking, thresholds, EVOLUTION_SIGNAL rules, agent-spec conventions.
reference/unified-spec/README.md Unified-spec recipe index, consolidation note, and legacy token policy.
reference/unified-spec/template-selection.md Choosing or escalating Full/Standard/Lite scope.
reference/unified-spec/unified-template.md Writing canonical L0/L1/L2/L3/L4/Meta packages.
reference/unified-spec/business-tech-translation.md Converting business intent into measurable audience-specific requirements.
reference/unified-spec/bdd-best-practices.md Authoring collaborative, declarative, testable L3 scenarios.
reference/unified-spec/cross-reference-guide.md Building and verifying bidirectional traceability.
reference/unified-spec/traceability-pitfalls.md Fixing orphan links, scope-inappropriate matrices, or non-SMART requirements.
reference/unified-spec/user-story-smells.md Checking story readiness, vertical slicing, and MoSCoW inflation.
reference/unified-spec/specification-anti-patterns.md Validating scope, audience, collaboration, and executable-spec quality.
reference/unified-spec/specification-calibration.md Running UNIFY and calibrating scope heuristics.
reference/unified-spec/interaction-triggers.md Serializing unified-package Ask First decisions.
reference/unified-spec/handoff-formats.md Consuming/emitting structured unified-package handoffs and legacy aliases.
reference/unified-spec/user-story-mapping.md Building story-map backbones, walking skeletons, and release slices.
reference/unified-spec/stakeholder-map.md Mapping Power × Interest and engagement/information flows.
reference/unified-spec/raci-matrix.md Assigning RACI/DACI/RAPID responsibility and decision rights.
reference/autorun-schema.md Emitting the AUTORUN _STEP_COMPLETE block — Scribe-specific Output/Next schema.
reference/format-conversion/ Converting between Markdown, Word, Excel, PDF, HTML (absorbed from morph)
_common/OPUS_5_AUTHORING.md Sizing the spec, thinking depth at PLAN, front-loading doc type/audience at SCAN. Critical: P3, P5.

Source: SKILL.md on GitHub

1 warning13d5 checks · Risk SAFE
  • Gen Agent Trust Hub13d

    No security issues were detected. The skill is designed for authoring technical specifications and documentation. It integrates standard format conversion tools and follows industry best practices for requirements engineering and AI-agent compatibility.

  • Socket13d

    No alerts

  • Snyk13d

    Risk: LOW · No issues

  • Runlayer6mo

    1/8 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 35ffd55. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 2 weeks ago

README badge

README badge for simota/agent-skills/scribe